← older: fast2__qwen3.6-27b__20260707-213441all runs · task boardnewer: fast__qwen3.6-27b__20260708-022105 →

fast2qwen3.6-35b-a3b20260707-224105

No notes for this run yet. Add runs/fast2__qwen3.6-35b-a3b__20260707-224105/NOTES.md — what was run & what changed, results, interpretation, next steps — and it will render here.

Run details

modelllama-local/qwen3.6-35b-a3bagentharnesses.subagents_pi:SubagentsPithinkingonreasoning budgetdirect (server/none)* — see journal for the authoritative mechanismmaxTokens / contextWindow65536 / 196608agent timeout ×2.0trials6 of 6 — 4 pass · 2 failmean reward0.67tokens (job total)65,017,966 in / 226,537 outstarted / finished2026-07-07T22:41 / 2026-07-07T23:47wall clock1h06m

Tasks

financial-document-processor — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	7m32s	6m39s	184027/8108	—	🔍 view

fix-ocaml-gc — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	32m09s	29m52s	59763850/140097	empty final message (no text, no tool call)long reasoning (15,718 chars)	🔍 view

git-multibranch — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	6m00s	5m11s	2638640/28514	claimed success but the verifier did NOT pass (heuristic)	🔍 view

headless-terminal — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	3m06s	2m10s	135793/6282	—	🔍 view

mailman — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	10m03s	8m49s	915728/17737	long reasoning (22,182 chars)	🔍 view

reshard-c4-data — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	7m36s	5m43s	1379928/25799	long reasoning (27,308 chars)	🔍 view